pincushion-mcp@1.11.25
Visual feedback as agent work packets. Stakeholders drop pins on your live app; your AI coding agent reads each pin (selector, screenshot, DOM, thread, acceptance criteria) via MCP and ships the fix.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe source establishes an explicit user-command path that changes AI-agent configuration. It does not establish lifecycle abuse, credential theft, destructive behavior, or covert persistence.
Decision evidence
public snapshot- The interactive setup wizard asks the user to select an editor before configuration is written.
- The setup core provides a writer that can add the package's MCP server to editor configuration.
- The package has a command-line server entrypoint and no install lifecycle hook in its manifest excerpt.
- The editor choice is explicit and may be skipped.
- Configuration is described and implemented as project-local and scoped to the package entry.
- Telemetry hashes the license key before using it as an identifier.
Source & flagged code
11 flaggedA single source file combines environment access, network access, and code or shell execution with blocking evidence.
mobile-wall.mjs#virtual:normalized:round1View on unpkg · L121Findings
Affected versions and remediation
This report applies to pincushion-mcp@1.11.25.
See all versions of pincushion-mcp for other recorded verdicts.
- Review the evidence and your use of pincushion-mcp@1.11.25 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.